# DeepSeek-V3.1-Terminus vs Phi 3 Mini 128k Instruct

> DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 29.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v3-1-terminus-vs-phi-3-mini-128k-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 10

## Summary

- They share 10 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 7 categories and Phi 3 Mini 128k Instruct in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1-Terminus leads 61.3 to 27.3.

## Snapshot

| | DeepSeek-V3.1-Terminus | Phi 3 Mini 128k Instruct |
|---|---|---|
| Provider | DeepSeek | Microsoft |
| Noometry Index | 42.6 | 29.1 |
| Rank | 96 | 303 |
| Context | 164K | — |
| Input $/M | $0.30 | — |
| Output $/M | $1 | — |
| Weights | Open | Open |

## Coding

- DeepSeek-V3.1-Terminus: 41.5 (#114)
- Phi 3 Mini 128k Instruct: 28.3 (#307)

| Benchmark | DeepSeek-V3.1-Terminus | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Coding | 1426 | 1040 |
| SciCode | 40.6% | — |
| BigCodeBench Instruct | — | 29.6% |
| BigCodeBench Complete | — | 40.6% |
| ALE-Bench | 745.17 | — |

## Reasoning

- DeepSeek-V3.1-Terminus: 25.7 (#126)
- Phi 3 Mini 128k Instruct: 18.7 (#254)

| Benchmark | DeepSeek-V3.1-Terminus | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1427 | 1028 |
| Kagi LLM Benchmark | 57.4% | — |
| CritPt | 1.7% | — |
| DTBench | 81.3% | — |
| LMCA | 28.6% | — |

## Math

- DeepSeek-V3.1-Terminus: 35.7 (#138)
- Phi 3 Mini 128k Instruct: 29.2 (#220)

| Benchmark | DeepSeek-V3.1-Terminus | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Math | 1402 | 1089 |

## Knowledge

- DeepSeek-V3.1-Terminus: —
- Phi 3 Mini 128k Instruct: 26.3 (#251)

| Benchmark | DeepSeek-V3.1-Terminus | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Expert | — | 984 |

## Multilingual

- DeepSeek-V3.1-Terminus: 52.3 (#87)
- Phi 3 Mini 128k Instruct: 25.4 (#280)

| Benchmark | DeepSeek-V3.1-Terminus | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Non-English | 1407 | 1000 |
| LMArena Russian | 1434 | 1004 |
| LMArena Chinese | — | 1016 |
| LMArena French | — | 1038 |
| LMArena German | — | 1006 |
| LMArena Japanese | — | 899 |
| LMArena Korean | — | 856 |
| LMArena Spanish | — | 1058 |

## Instruction Following

- DeepSeek-V3.1-Terminus: 74.4 (#96)
- Phi 3 Mini 128k Instruct: 52.1 (#289)

| Benchmark | DeepSeek-V3.1-Terminus | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Instruction Following | 1406 | 1023 |

## Long Context

- DeepSeek-V3.1-Terminus: 43.5 (#88)
- Phi 3 Mini 128k Instruct: 30.3 (#284)

| Benchmark | DeepSeek-V3.1-Terminus | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Longer Query | 1426 | 996 |

## Writing & Preference

- DeepSeek-V3.1-Terminus: 61.3 (#87)
- Phi 3 Mini 128k Instruct: 27.3 (#296)

| Benchmark | DeepSeek-V3.1-Terminus | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Text | 1420 | 1050 |
| LMArena Creative Writing | 1404 | 1024 |
| LMArena Multi-Turn | 1411 | 989 |

## FAQ

### Is DeepSeek-V3.1-Terminus better than Phi 3 Mini 128k Instruct?

DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 29.1 on the Noometry Index.

### Is DeepSeek-V3.1-Terminus or Phi 3 Mini 128k Instruct better for coding?

DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 41.5 versus 28.3 in the Noometry coding category.

### How many benchmarks do DeepSeek-V3.1-Terminus and Phi 3 Mini 128k Instruct share?

10 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Phi 3 Mini 128k Instruct has 19.